© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5712
    Prev
    Next
    INDEX
    Explanations

    code syntax

    oai_token-act-pair · gemini-2.0-flash

    Code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.91
    .
    -0.84
    :
    -0.76
    -
    -0.75
     Bison
    -0.70
     cockroaches
    -0.66
     harem
    -0.66
     bellows
    -0.65
     yoke
    -0.65
     Mep
    -0.64
    POSITIVE LOGITS
     enfans
    1.02
     avoient
    0.94
     générations
    0.84
     varandra
    0.84
     négociations
    0.83
     stället
    0.82
     gouvernements
    0.82
     feroit
    0.81
     skydd
    0.81
     quæ
    0.81
    Activations Density 20.060%

    No Known Activations